Automating the Detection of Linguistic Intergroup Bias Through Computerized Language Analysis
Bibliographic record
Abstract
Linguistic bias is the differential use of abstraction, or other linguistic mechanisms, for the same behavior by members of different groups. Abstraction is defined by the Linguistic Category Model (LCM), which defines a continuum of words from concrete to abstract. Linguistic Intergroup Bias (LIB) characterizes the tendency for people to use abstract words for undesirable outgroup and desirable ingroup behavior and concrete words for desirable outgroup and undesirable ingroup behavior. Thus, by examining abstraction in a text, we can understand the implicit attitudes of the author. Yet, research is currently stifled by the time-consuming and resource-intensive method of manual coding. In this study, we aim to develop an automated method to code for LIB. We compiled various techniques, including forms of sentence tokenization, sentiment analysis, and abstraction coding. All methods provided scores that were a good approximation of manually coded scores, which is promising and suggests that more complex methods for LIB coding may be unnecessary. We recommend automated approaches using CoreNLP sentiment analysis and LCM Dictionary abstraction coding.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".